Yonatan Bitton

multimodal learning (7) vision-language model (5) visual question answering (5) large language model (3) text-to-image generation (3) zero-shot learning (3) benchmark evaluation (3) contrastive learning (2) data augmentation (2) automatic evaluation (2) vision language model (2) clip model (2) instruction following (2) image captioning (2) benchmark dataset (2) data filtering (2) commonsense knowledge (1) question answering (1) scene understanding (1) knowledge distillation (1)